Re: [PATCH RFC] bpf: Add support for reading user pointers

[Peter Zijlstra]

On Fri, May 03, 2019 at 09:49:35AM -0400, Joel Fernandes wrote:
> In
> particular, we learnt with extensive discussions that user/kernel pointers
> are not necessarily distinguishable purely based on their address.

This is correct; a number of architectures have a completely separate
user and kernel address space. Much like how the old i386 4G:4G patches
worked.